Explore the vast range of titles available.

Health care is one of the most exciting frontiers in data mining and machine learning. Successful adoption of electronic health records (EHRs) created an explosion in digital clinical data available for analysis, but progress in machine learning for healthcare research has been difficult to measure because of the absence of publicly available benchmark data sets. To address this problem, we propose four clinical prediction benchmarks using data derived from the publicly available Medical Information Mart for Intensive Care (MIMIC-III) database. These tasks cover a range of clinical problems including modeling risk of mortality, forecasting length of stay, detecting physiologic decline, and phenotype classification. We propose strong linear and neural baselines for all four tasks and evaluate the effect of deep supervision, multitask training and data-specific architectural modifications on the performance of neural models.

Surgery is a mainstay treatment for patients with solid tumours. However, despite surgical resection with a curative intent and numerous advances in the effectiveness of (neo)adjuvant therapies, metastatic disease remains common and carries a high risk of mortality. The biological perturbations that accompany the surgical stress response and the pharmacological effects of anaesthetic drugs, paradoxically, might also promote disease recurrence or the progression of metastatic disease. When cancer cells persist after surgery, either locally or at undiagnosed distant sites, neuroendocrine, immune, and metabolic pathways activated in response to surgery and/or anaesthesia might promote their survival and proliferation. A consequence of this effect is that minimal residual disease might then escape equilibrium and progress to metastatic disease. Herein, we discuss the most promising proposals for the refinement of perioperative care that might address these challenges. We outline the rationale and early evidence for the adaptation of anaesthetic techniques and the strategic use of anti-adrenergic, anti-inflammatory, and/or antithrombotic therapies. Many of these strategies are currently under evaluation in large-cohort trials and hold promise as affordable, readily available interventions that will improve the postoperative recurrence-free survival of patients with cancer.

Cancer remains a leading causes of death worldwide and an elevated systemic inflammatory response (SIR) is associated with reduced survival in patients with operable cancer. This review aims to examine the evidence for the role of systemic inflammation based prognostic scores in patients with operable cancers. A wide-ranging literature review using targeted medical subject headings for human studies in English was carried out in the MEDLINE, EMBASE, and CDSR databases until the end of 2016. The SIR has independent prognostic value, across tumour types and geographical locations. In particular neutrophil lymphocyte ratio (NLR) (n = 158), platelet lymphocyte ratio (PLR) (n = 68), lymphocyte monocyte ratio (LMR) (n = 21) and Glasgow Prognostic Score/ modified Glasgow Prognostic Score (GPS/mGPS) (n = 60) were consistently validated. On meta-analysis there was a significant relationship between elevated NLR and overall survival (OS) (p < 0.00001)/ cancer specific survival (CSS) (p < 0.00001), between elevated LMR and OS (p < 0.00001)/CSS (p < 0.00001), and elevated PLR and OS (p < 0.00001)/CSS (p = 0.005). There was also a significant relationship between elevated GPS/mGPS and OS (p < 0.00001)/CSS (p < 0.00001). These results consolidate the prognostic value of the NLR, PLR, LMR and GPS/mGPS in patients with resectable cancers. This is particularly true for the NLR/GPS/mGPS which should form part of the routine preoperative and postoperative workup.

We systematically searched available databases. We reviewed 6,143 studies published from 1833 to 2017. Reports in English, French, German, Italian, and Spanish were considered, as were publications in other languages if definitive treatment and recurrence at specific follow-up times were described in an English abstract. We assessed data in the manner of a meta-analysis of RCTs; further we assessed non-RCTs in the manner of a merged data analysis. In the RCT analysis including 11,730 patients, Limberg & Dufourmentel operations were associated with low recurrence of 0.6% (95%CI 0.3–0.9%) 12 months and 1.8% (95%CI 1.1–2.4%) respectively 24 months postoperatively. Analysing 89,583 patients from RCTs and non-RCTs, the Karydakis & Bascom approaches were associated with recurrence of only 0.2% (95%CI 0.1–0.3%) 12 months and 0.6% (95%CI 0.5–0.8%) 24 months postoperatively. Primary midline closure exhibited long-term recurrence up to 67.9% (95%CI 53.3–82.4%) 240 months post-surgery. For most procedures, only a few RCTs without long term follow up data exist, but substitute data from numerous non-RCTs are available. Recurrence in PSD is highly dependent on surgical procedure and by follow-up time; both must be considered when drawing conclusions regarding the efficacy of a procedure.

BackgroundGastroenteropancreatic neuroendocrine neoplasms (GEPNENs) are heterogeneous in clinical course, biology, and outcomes. The NETPET score predicts survival by scoring uptake on dual [68Ga]DOTATATE and [18F]FDG PET/CT scans. We aimed to validate previous single-centre findings in a multicentre, international study.MethodsDual scans were assigned a NETPET score of P1 (DOTATATE positive/FDG negative), P2–4 (DOTATATE positive/FDG positive), or P5 (DOTATATE negative/FDG positive). NETPET score, histological grade, age at diagnosis, and presence/absence of extrahepatic disease were compared to overall survival/time to progression on univariate and multivariate analysis.Results319 metastatic/unresectable GEPNEN patients were included. The NETPET score was significantly associated with overall survival and time to progression on univariate and multivariate analysis (all p < 0.01). Median overall survival/time to progression was 101.8/25.5 months for P1, 46.5/16.7 months for P2–4, and 11.5/6.6 months for P5. Histological grade correlated with overall survival and time to progression on univariate and multivariate analysis (all p < 0.01), while presence/absence of extrahepatic disease did not. Age at diagnosis correlated with overall survival on univariate and multivariate analysis (p < 0.01). The NETPET score also correlated with histological grade (p < 0.001).ConclusionThis study validates the NETPET score as a prognostic biomarker in metastatic GEPNENs, capturing the complexity of dual PET imaging.

IntroductionColorectal cancer is the fourth most common cancer in the UK. There remains a need for improved risk stratification following curative resection. Circulating-tumour DNA (ctDNA) has gained particular interest as a cancer biomarker in recent years. We performed a systematic review to assess the utility of ctDNA in identifying minimal residual disease in colorectal cancer.MethodsStudies were included if ctDNA was measured following curative surgery and long-term outcomes were assessed. Studies were excluded if the manuscript could not be obtained from the British Library or were not available in English.ResultsThirty-seven studies met the inclusion criteria, involving 3002 patients. Hazard ratios (HRs) for progression-free survival (PFS) were available in 21 studies. A meta-analysis using a random effects model demonstrated poorer PFS associated with ctDNA detection at the first liquid biopsy post-surgery [HR: 6.92 CI: 4.49–10.64 p < 0.00001]. This effect was also seen in subgroup analysis by disease extent, adjuvant chemotherapy and assay type.DiscussionHere we demonstrate that ctDNA detection post-surgery is associated with a greater propensity to disease relapse and is an independent indicator of poor prognosis. Prior to incorporation into clinical practice, consensus around timing of measurements and assay methodology are critical.Protocol registrationThe protocol for this review is registered on PROSPERO (CRD42021261569).

In rural China, where healthcare relies on village doctors (nonspecialized practitioners who work exclusively in their village clinics), delivering integrated atrial fibrillation (AF) management poses challenges. We developed a telemedicine-based, village doctor-led integrated care model and conducted a cluster randomized clinical trial to assess its efficacy compared to usual care. A total of 30 village clinics were randomly assigned (1:1) to the intervention or control group, with 1,039 village residents aged ≥65 years with AF (44.3% women) recruited. The primary outcome in stage 1 is adherence to integrated AF care at 12 months. In stage 2, the primary outcome is a composite of cardiovascular death, all strokes, heart failure or acute coronary syndrome hospitalization, and AF emergency visits over 36 months. Both primary outcomes were met. At 12 months, 33.1% in the telemedicine-based, village doctor-led care group and 8.7% in the usual care group met all criteria for integrated AF care (between-group difference, 24.4% (95% confidence interval (CI), 18.3–30.5%); P  < 0.001). Over 34.0 months, 41.8% in the telemedicine-based, village doctor-led care group and 10.3% in the usual care group met all criteria for integrated AF care ( P  < 0.001). The rate of the composite cardiovascular event outcome was lower in the telemedicine-based, village doctor-led care group than in the usual care group (6.2% versus 9.6% per year; hazard ratio, 0.64 (95% CI, 0.50–0.82); P  < 0.001). Our trial intervention by this telemedicine-based integrated care delivery model of AF care in rural villages demonstrates better adherence and improved clinical outcomes compared to usual care. ClinicalTrials.gov registration: NCT04622514 . A cluster randomized trial in China shows that telemedicine-based, village doctor-led delivery of integrated care reduced the occurrence of adverse cardiovascular events and hospitalizations in older adults with atrial fibrillation.

In this study, we utilized data from the Surveillance, Epidemiology, and End Results (SEER) database to predict the glioblastoma patients’ survival outcomes. To assess dataset skewness and detect feature importance, we applied Pearson's second coefficient test of skewness and the Ordinary Least Squares method, respectively. Using two sampling strategies, holdout and five-fold cross-validation, we developed five machine learning (ML) models alongside a feed-forward deep neural network (DNN) for the multiclass classification and regression prediction of glioblastoma patient survival. After balancing the classification and regression datasets, we obtained 46,340 and 28,573 samples, respectively. Shapley additive explanations (SHAP) were then used to explain the decision-making process of the best model. In both classification and regression tasks, as well as across holdout and cross-validation sampling strategies, the DNN consistently outperformed the ML models. Notably, the accuracy were 90.25% and 90.22% for holdout and five-fold cross-validation, respectively, while the corresponding R 2 values were 0.6565 and 0.6622. SHAP analysis revealed the importance of age at diagnosis as the most influential feature in the DNN's survival predictions. These findings suggest that the DNN holds promise as a practical auxiliary tool for clinicians, aiding them in optimal decision-making concerning the treatment and care trajectories for glioblastoma patients.

Chromosome banding analysis (CBA) remains the standard-of-care for structural variant (SV) assessment in MDS. Optical genome mapping (OGM) is a novel, non-sequencing-based technique for high-resolution genome-wide SV profiling (SVP). We explored the clinical value of SVP by OGM in 101 consecutive, newly diagnosed MDS patients from a single-center, who underwent standard-of-care cytogenetic and targeted NGS studies. OGM detected 383 clinically significant, recurrent and novel SVs. Of these, 224 (51%) SVs, seen across 34% of patients, were cryptic by CBA (included rearrangements involving MECOM, NUP98::PRRX2, KMT2A partial tandem duplications among others). SVP decreased the proportion of normal karyotype by 16%, identified complex genomes (17%), chromothripsis (6%) and generated informative results in both patients with insufficient metaphases. Precise gene/exon-level mapping allowed assessment of clinically relevant biomarkers (TP53 allele status, KMT2A-PTD) without additional testing. SV data was complementary to NGS. When applied in retrospect, OGM results changed the comprehensive cytogenetic scoring system (CCSS) and R-IPSS risk-groups in 21% and 17% patients respectively with an improved prediction of prognosis. By multivariate analysis, CCSS by OGM only (not CBA), TP53 mutation and BM blasts independently predicted survival. This is the first and largest study reporting the value of combined SVP and NGS for MDS prognostication.

The number of HLA-haploidentical hematopoietic cell transplants continues to increase worldwide due to recent improvements in outcomes, allowing more patients with hematological malignancies and non-malignant disorders to benefit from this procedure and have a chance to cure their disease. Despite these encouraging results, questions remain as multiple donors are usually available for transplantation, and choosing the best HLA-haploidentical donor for transplantation remains a challenge. Several approaches to haploidentical transplantation have been developed over time and, based on the graft received, can be grouped as follows: T-cell depleted haploidentical transplants, either complete or partial, or with T-cell replete grafts, performed with post-transplant cyclophosphamide-based graft-versus-host disease (GVHD) prophylaxis, or G-CSF-primed bone marrow graft and enhanced GVHD prophylaxis. Carefully selecting the donor can help optimize transplant outcomes for recipients of haploidentical donor transplants. Variables usually considered in the donor selection include presence of donor-specific antibodies in the recipient, donor age, donor/recipient gender and ABO combinations, and immunogenic variables, such as natural killer cell alloreactivity or KIR haplotype. Here we provide a comprehensive review of available evidence for selecting haploidentical donors for transplantation, and summarize the recommendations from the European Society for Blood and Marrow Transplantation (EBMT) on donor selection for different transplant platforms.